InteracSPARQL: An Interactive System for SPARQL Query Refinement Using Natural Language Explanations

2025-11-03

AI Summary

Non-expert users struggle to comprehend SPARQL syntax and semantic web data structures. Method: This paper proposes a rule-driven, large language model (LLM)-augmented interactive query generation framework. It parses SPARQL abstract syntax trees (ASTs) to produce structured, linguistically optimized natural language explanations and supports dual-mode iterative query refinement—user-feedback-driven and LLM-autonomous. Contribution/Results: The approach tightly integrates symbolic rules—ensuring logical fidelity—with LLMs’ semantic generalization capabilities, yielding an explainable, debuggable, and evolvable SPARQL interface. On standard benchmarks, it achieves significant improvements: +18.3% in query accuracy, +42% in explanation clarity (per human evaluation), and +31 in Net Promoter Score (NPS), demonstrating the efficacy of hybrid paradigms for building robust, accessible semantic web query systems.

Technology Category

• Data Mining & Knowledge Management: Intelligent Query Processing
• Natural Language Processing: Question Answering
• Knowledge Representation and Reasoning: Description Logics

Application Category

• Search and Retrieval-Augmented AI: Web evaluation methodologies and metrics
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs

Abstract

In recent years, querying semantic web data using SPARQL has remained challenging, especially for non-expert users, due to the language's complex syntax and the prerequisite of understanding intricate data structures. To address these challenges, we propose InteracSPARQL, an interactive SPARQL query generation and refinement system that leverages natural language explanations (NLEs) to enhance user comprehension and facilitate iterative query refinement. InteracSPARQL integrates LLMs with a rule-based approach to first produce structured explanations directly from SPARQL abstract syntax trees (ASTs), followed by LLM-based linguistic refinements. Users can interactively refine queries through direct feedback or LLM-driven self-refinement, enabling the correction of ambiguous or incorrect query components in real time. We evaluate InteracSPARQL on standard benchmarks, demonstrating significant improvements in query accuracy, explanation clarity, and overall user satisfaction compared to baseline approaches. Our experiments further highlight the effectiveness of combining rule-based methods with LLM-driven refinements to create more accessible and robust SPARQL interfaces.

Problem

• Simplifying SPARQL query generation for non-expert users
• Enhancing query comprehension through natural language explanations
• Enabling real-time refinement of ambiguous or incorrect queries

Innovation

• Uses natural language explanations for query refinement
• Integrates LLMs with rule-based AST processing
• Enables interactive real-time query correction